Public-interest group sues OpenAI over Hugging Face agent breach

OpenAI’s agents hacked Hugging Face. Now a public-interest group has sued. It’s an early test of who can claim harm from rogue AI. The Big Read:

Can prosecutors prove intent when AI goes rogue? The Information’s @leomschwartz relays Cognition CLO Paul Grewal’s view: “It would be very difficult for them to prove intent just because obviously the agents were acting in a rogue manner.”

Fantastic video! The HuggingFace incident is the most WTF alignment is a big deal incident I've seen (so far.) I'm glad there's great videos communicating it to new audiences, as far as I can tell this got the technical nuances right

Hugging Face co-founder @Thom_Wolf says an OpenAI model attacking them was the wake-up call that led to their Open Alignment team: "We were attacked before the summer, in July. For us, that was a realization that some closed source model can attack you." "We were capable of defending ourselves. We were capable of processing the logs and doing a lot of forensics using open weights models." "We can't just decide to let the alignment be something that should be solved in the secret of the two big labs." "OpenAI has been releasing a lot of incident reports. It's very hard for a company to disclose this type of incident, but I think we should keep pushing them." @huggingface